# reference.myneogroup.com - official reference site of My NEO Group.
# All public pages and files may be read by search engines and by AI search, retrieval and training agents.
# Content signals (contentsignals.org): search = building a search index and providing search results;
# ai-input = inputting content into AI models, for example for retrieval and grounded answers; ai-train = training or fine-tuning AI models.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Search engines: Google, Microsoft Bing (also the index of Copilot), Apple
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# OpenAI: ChatGPT search, user requests, model training, ad checks
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: OAI-AdsBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Anthropic: Claude search, user requests, model training
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Google: Gemini training and grounding (a control token, not a crawler)
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Apple: Apple Intelligence training (a control token, not a crawler)
User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Perplexity: search index, user requests
User-agent: PerplexityBot
User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Meta: Meta AI search, model training, user requests
User-agent: meta-webindexer
User-agent: meta-externalagent
User-agent: meta-externalfetcher
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Mistral: search index, user requests, model training
User-agent: MistralAI-Index
User-agent: MistralAI-User
User-agent: MistralAI-Training
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Common Crawl: open web corpus
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

Sitemap: https://reference.myneogroup.com/sitemap.xml